conftrace_

jailbreak defense

29 papers

Explore in graph

Co-occurring keywords

large language model (13587) jailbreak attack (225) model safety (101) safety alignment (178) adversarial learning (1595) adversarial defense (325) adversarial attack (1621) ai safety (235) adversarial robustness (1341) llm safety (67)

Papers

MirrorShield: Towards Dynamic Adaptive Defense Against Jailbreaks via Entropy-Guided Mirror Crafting AAAI 2026
EigenShield: Inference-Time, Model-Agnostic Jailbreaking Defense via Causal Subspace Filtering AAAI 2026
SafetyMem: Adaptive Jailbreak Defense via Dual-Component Safety Memory ACL 2026
Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models AAAI 2026
SafetyReminder: Reviving Delayed Safety Awareness of Vision-Language Models to Defend Against Jailbreak Attacks AAAI 2026
SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning EMNLP 2025
Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking EMNLP 2025
AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders EMNLP 2025
MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models EMNLP 2025
Unraveling the Mystery: Defending Against Jailbreak Attacks Via Unearthing Real Intention COLING 2025
DeTAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification ACL 2025
X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Jailbreak Attacks without Compromising Usability EMNLP 2025
SecDecoding: Steerable Decoding for Safer LLM Generation EMNLP 2025
Proxy Barrier: A Hidden Repeater Layer Defense Against System Prompt Leakage and Jailbreaking EMNLP 2025
Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks CVPR 2025
Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update AAAI 2025
How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation EMNLP 2025
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender EMNLP 2025
Multilingual Collaborative Defense for Large Language Models EMNLP 2025
Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level ACL 2025
Representation Bending for Large Language Model Safety ACL 2025
Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refine NAACL 2025
Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders EMNLP 2025
Protecting Your LLMs with Information Bottleneck NIPS 2024
BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment NIPS 2024